Vijayalaksmi Murli
Research Subjects
Vijayalaksmi Murli has a total of 22 co-authors. Here are the top co-authors by number of shared publications:
- Sangeeta Oswal
VESIT
3 shared publications - Subhash Shinde
Department of Computer Engineering, Lokmanya Tilak College of Engineering, Navi Mumbai
3 shared publications - Apeksha Kulkarni
Vivekanand Education Society’s Institute of Technology
2 shared publications - Dhirendra Mishra
Department of Computer Engineering, Narsee Monjee Institute of Management Studies, Mumbai, Maharashtra 400056, India
2 shared publications - Mahesh Mali
NMIMS Deemed be Univ, Mukesh Patel Sch Technol Management & Engn, Dept Comp Engn, Mumbai, Maharashtra, India
2 shared publications - Shalu Chopra
Vivekanand Education Society’s Institute of Technology, Collector’s Colony, Chembur
2 shared publications
Latest Publications
- Open Access
- 1 December 2025
- Published by Institute of Advanced Engineering and Science in International Journal of Advances in Applied Sciences
- Vol. 14 (4)
Unveiling anomalies in industrial control systems: a kernel SHAP-based approach with temporal convolution autoencoder
Industrial control systems (ICS) are often the target of cyber-attacks, leading to undesirable consequences. ICSs operate without human supervision, making them vulnerable to adversaries. In recent years, numerous deep learning-based solutions have demonstrated their efficiency in detecting anomalies in ICSs. However, there is a lack of ability to pinpoint the sensors and actuators that contributed to the anomaly. In this research work, we use kernel Shapley additive explanations (SHAP) to explain anomalies detected by a temporal convolution autoencoder (TCAE). The proposed TCAE model handles the long-term dependency effectively and is computationally effective on a large dataset. A comprehensive explanation is provided, focusing on the feature that contributed to the anomaly for each identified attack. The SHAP values are extracted for each identified attack and visually depict the feature that contributed to the anomaly for each attack, helping the expert to handle the attack and build user trust.
- 1 December 2025
- Published by Institute of Advanced Engineering and Science in International Journal of Advances in Applied Sciences
- Vol. 14 (4)
Open AccessUnveiling anomalies in industrial control systems: a kernel SHAP-based approach with temporal convolution autoencoder
Industrial control systems (ICS) are often the target of cyber-attacks, leading to undesirable consequences. ICSs operate without human supervision, making them vulnerable to adversaries. In recent years, numerous deep learning-based solutions have demonstrated their efficiency in detecting anomalies in ICSs. However, there is a lack of ability to pinpoint the sensors and actuators that contributed to the anomaly. In this research work, we use kernel Shapley additive explanations (SHAP) to explain anomalies detected by a temporal convolution autoencoder (TCAE). The proposed TCAE model handles the long-term dependency effectively and is computationally effective on a large dataset. A comprehensive explanation is provided, focusing on the feature that contributed to the anomaly for each identified attack. The SHAP values are extracted for each identified attack and visually depict the feature that contributed to the anomaly for each attack, helping the expert to handle the attack and build user trust.
- 22 June 2025
- Published by Springer Nature
- p. 15-30
Object Detection Using Deep Learning
- 19 January 2025
- Published by Springer Nature
- p. 15-27
An Efficient Image Denoising Using Convolutional Neural Network
- 19 January 2025
- Published by Springer Nature
- p. 15-27
An Efficient Image Denoising Using Convolutional Neural Network
- 5 November 2023
- Published by Springer Nature
- p. 59-71
Deep Learning-Based Anomaly Detection in Cyber-Physical System
- 5 November 2023
- Published by Springer Nature
- p. 59-71
Deep Learning-Based Anomaly Detection in Cyber-Physical System
- 20 July 2023
- Published by Springer Nature
- p. 271-286
Revolutionising Public Restrooms: Smart Urinal System with Ammonia Detection and Automated Flushing
- 20 July 2023
- Published by Springer Nature
- p. 271-286
Revolutionising Public Restrooms: Smart Urinal System with Ammonia Detection and Automated Flushing
- 14 July 2023
- Published by Springer Nature
- p. 221-234
A Survey of Statistical, Machine Learning, and Deep Learning-Based Anomaly Detection Techniques for Time Series
- 14 July 2023
- Published by Springer Nature
- p. 221-234
A Survey of Statistical, Machine Learning, and Deep Learning-Based Anomaly Detection Techniques for Time Series
- Open Access
- 4 January 2023
- Published by Springer Nature in Research Square
MF-RISE : Benchmarking for Multifaceted Recommender System Engine
The advent of the information age has led tothe availability of overwhelming choices of products to userswhich create need of various Recommendation Systems (RS). Recommendation System belongs to the methods of InformationRetrieval, Data Mining and Machine Learning algorithms. Multifaceted Recommendation System Engine (MF-RISE) helpthe users to get personalized recommendations, helps users to select correct product from wide range of products using userfeedback, ratings and reviews provided by users. In real-world scenarios, recommenders have many non-functionalrequirements of technical nature and must handle huge amountdata. Evaluation of Multifaceted Recommendation System Enginemust take these issues into account in order to be producemaximum useful recommendations. The many researchers have proposed a wide range of recommendationsystems algorithms. This study investigates there are threepopular existing types of recommendation systems algorithms, Collaborative Filtering (CF), Content-Based Filtering (CB), andHybrid Recommendation System. The MovieLens dataset with its3 variants was utilized for the purpose of this study. The studiedevaluation methods consider both quantitative and qualitativeaspects of algorithm with many evaluation parameters like meansquared error (MSE), root mean squared error (RMSE), Test Timeand Fit Time are calculated for each recommender algorithmimplementation. The study identifies the gaps and challengesfaced by every recommender algorithm. This study will alsohelp researchers to propose new recommendation algorithms by overcoming identified research gaps and challenges of existing algorithms.
- 4 January 2023
- Published by Springer Nature in Research Square
Open AccessMF-RISE : Benchmarking for Multifaceted Recommender System Engine
The advent of the information age has led tothe availability of overwhelming choices of products to userswhich create need of various Recommendation Systems (RS). Recommendation System belongs to the methods of InformationRetrieval, Data Mining and Machine Learning algorithms. Multifaceted Recommendation System Engine (MF-RISE) helpthe users to get personalized recommendations, helps users to select correct product from wide range of products using userfeedback, ratings and reviews provided by users. In real-world scenarios, recommenders have many non-functionalrequirements of technical nature and must handle huge amountdata. Evaluation of Multifaceted Recommendation System Enginemust take these issues into account in order to be producemaximum useful recommendations. The many researchers have proposed a wide range of recommendationsystems algorithms. This study investigates there are threepopular existing types of recommendation systems algorithms, Collaborative Filtering (CF), Content-Based Filtering (CB), andHybrid Recommendation System. The MovieLens dataset with its3 variants was utilized for the purpose of this study. The studiedevaluation methods consider both quantitative and qualitativeaspects of algorithm with many evaluation parameters like meansquared error (MSE), root mean squared error (RMSE), Test Timeand Fit Time are calculated for each recommender algorithmimplementation. The study identifies the gaps and challengesfaced by every recommender algorithm. This study will alsohelp researchers to propose new recommendation algorithms by overcoming identified research gaps and challenges of existing algorithms.
- 1 November 2022
- Published by Springer Nature
- p. 665-673
Comparative Study of Recommendation Algorithms on Yelp Dataset
- 1 November 2022
- Published by Springer Nature
- p. 665-673
Comparative Study of Recommendation Algorithms on Yelp Dataset
- 2 August 2022
- Published by Springer Nature
- p. 49-64
Discernment of Unsolicited Internet Spamdexing Using Graph Theory
- 2 August 2022
- Published by Springer Nature
- p. 49-64
Discernment of Unsolicited Internet Spamdexing Using Graph Theory
- 31 March 2022
- Published by Springer Nature
- p. 355-365
Spirochaeta Bacteria Detection Using an Effective Semantic Segmentation Technique
- 31 March 2022
- Published by Springer Nature
- p. 355-365
Spirochaeta Bacteria Detection Using an Effective Semantic Segmentation Technique